🔬Causal Models Need Causal Data - Xaira’s X-Cell model for Drug Discovery (Bo Wang & Ci Chu, Chief Discovery Officer & Chief AI Scientist)

Xaira Therapeutics is advancing drug discovery by integrating AI-native platforms with high-throughput biological experimentation. The core innovation, the "virtual cell" model X-Cell, predicts cellular responses to genetic and chemical perturbations by leveraging massive, high-quality causal datasets generated through Perturb-Seq. Unlike descriptive models trained on observational data, X-Cell utilizes diffusion language models to capture complex regulatory networks and generalize across unseen cell types and contexts. By combining diverse biological priors—such as protein-protein interaction networks and literature-based embeddings—with genome-wide perturbation data, the platform aims to transform drug development from artisanal trial-and-error into a predictive engineering discipline. This approach addresses critical bottlenecks in translating laboratory findings to clinical success, ultimately seeking to improve therapeutic outcomes by accurately modeling how interventions influence cellular states and patient responses.